Speech & Audio

Extending ASR Evaluation Resources for Modern Greek Dialects EACL 2026 Eyaa-Tom 26, Yodi-Mantissa and Lom Bench: A Community Benchmark for TTS in Local Languages EACL 2026 FC-TTS: Style and Timbre Control in Zero-Shot Text-to-Speech with Disentangled Speech Representations ACL 2026 From Naturalness to Norms: Interactional Cultural Competence for SpeechLMs ACL 2026 Full Fine-Tuning vs. Parameter-Efficient Adaptation for Low-Resource African ASR: A Controlled Study with Whisper-Small EACL 2026 Graph-Based Phonetic Error Correction of Noisy ASR ACL 2026 HalluAudio: A Comprehensive Benchmark for Hallucination Detection in Large Audio-Language Models ACL 2026 Hearing the Room Through the Shape of the Drum: Modal-Guided Sound Recovery from Multi-Point Surface Vibrations CVPR 2026 Hierarchical Codec Diffusion for Video-to-Speech Generation CVPR 2026 Hierarchical Policy Optimization for Simultaneous Translation of Unbounded Speech ACL 2026 HiKE: Hierarchical Evaluation Framework for Korean-English Code-Switching Speech Recognition EACL 2026 How Far Can We Go With Synthetic Data for Audio-Visual Sound Source Localization? CVPR 2026 ImmersiveTTS: Environment-Aware Text-to-Speech with Multimodal Diffusion Transformer and Domain-Specific Representation Alignment ACL 2026 IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech AAAI 2026 LASER: Lip Landmark Assisted Speaker Detection for Robustness WACV 2026 LCMA-SRT: Language-Conditional Mixture-of-Experts Adapters for Joint Multilingual Speech Recognition and Translation ACL 2026 Learning from Scarcity: Building and Benchmarking Speech Technology for Sukuma. EACL 2026 Linguistically Informed Evaluation of Multilingual ASR for African Languages EACL 2026 Linguistically Informed Tokenization Improves ASR for Underresourced Languages EACL 2026 Listening Like Humans: Semantics-Guided Noise-Robust Multimodal Speech Recognition ACL 2026 Listen like a Teacher: Mitigating Whisper Hallucinations Using Adaptive Layer Attention and Knowledge Distillation AAAI 2026 LLM-ForcedAligner: A Non-Autoregressive and Accurate LLM-Based Forced Aligner for Multilingual and Long-Form Speech ACL 2026 MauBERT: Universal Phonetic Inductive Biases for Few-Shot Acoustic Units Discovery ACL 2026 MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flows ACL 2026 Mixture-of-Experts with Intermediate CTC Supervision for Accented Speech Recognition ACL 2026